search

Nota-NetsPresso / BK-SDM

A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ECCV'24]
Other
238 stars 16 forks source link

issue about training iterations #49

Closed StormArcher closed 8 months ago

StormArcher commented 8 months ago

We note the readme show training BK-SDM-Base need 50K interations， while we find in the "kd_train.py" show --max_train_steps=400K \, so can we think the 50K is good enough?

bokyeong1015 commented 8 months ago

Hi,

Although our script specifies --max_train_steps=400000, we released the checkpoints at the exact 50000-th step as described in our paper.

Evaluating at 50K iterations was primarily done to reduce training costs (while yielding acceptable performance). Extending the number of iterations and using more data could lead to improved results.

For more details, please refer to the table below in our paper. image.